[Colloq] ECE Hiring talk by Jason Corso

[Robert Platt]

Hi there --

Jason Corso, an old colleague of mine, is giving a faculty candidate 
talk in ECE next Thursday (2/12) at 1:30-3:00PM in 442 DA. Jason does 
Computer Vision and Machine Learning. Here is the announcement:

Title: Perceiving Action in Space-Time: Computational and Human Perspectives

Abstract:
Humans are highly articulated, which leads to complex and idiosyncratic 
actions in space-time.  This complexity has challenged computational 
models of human action for some time now, and yet humans themselves are 
highly adept at parsing action.  In this talk, I will motivate the 
challenge of interpreting human action from spatial, temporal, and 
spatiotemporal points of view.  Then, I will present both computational 
and human perspectives on modeling action.  First, I will describe how 
video can be decomposed into a multilevel semantic scale-space using a 
two-part Markov approximation framework.  Within this semantic 
scale-space, we have conducted a visual psychophysical study of how 
humans perceive action, and I will report our findings in that study.

Second, I will present a pair of computational models for human action.  
The first method, called Action Bank, creates a high-level action space 
that is spanned by individual space-time actions.  Query videos are 
projected into this action space and non-linear classifiers are learned 
for recognition.  The second method proposes a ranking conditional 
random field model for category-independent action inference.  The model 
seeks a differentiation between motion and action by incorporating both 
local action evidence and a neighborhood ordering criteria.  Experiments 
demonstrate how space-time, action-specific modeling can outperform 
motion background subtraction and human detection, as well as other 
models of ranking. Time-permitting, I will relate these findings to 
other work in my group in computational neuroscience and cognitive robotics.


Bio:

Corso is an associate professor of Computer Science and Engineering at 
SUNY Buffalo. He received his Ph.D. at The Johns Hopkins University in 
2006 (from the Computational Interaction with Physical Systems Lab), the 
M.S.E Degree from The Johns Hopkins University in 2002 and the B.S. 
Degree with honors from Loyola College In Maryland.  He spent two years 
as a post-doctoral fellow at the University of California, Los Angeles 
affiliated with Medical Imaging Informatics, the Laboratory of Neuro 
Imaging, and the Center for Image and Vision Science.   He is the 
recipient of the Army Research Office Young Investigator Award 2010 
(robotics), NSF CAREER award 2009 (computer vision), SUNY Buffalo Young 
Investigator Award 2011, a member of the 2009 DARPA Computer Science 
Study Group (data mining), and a recipient of the Link Foundation 
Fellowship in Advanced Simulation and Training (physically-grounded 
vision).  Corso has authored more than ninety peer-reviewed papers on 
topics of his research interest including computer vision, robotics, 
data science, and medical imaging.  He is a member of the AAAI, IEEE and 
the ACM.  He is PI on more than $5 million in research funding from 
major federal agencies, including NSF, NIH, DARPA, ARO, and IARPA.